Subject: [merged] memcg-slab-rcu-protect-memcg_params-for-root-caches.patch removed from -mm tree
To: vdavydov@xxxxxxxxxxxxx,bsingharora@xxxxxxxxx,cl@xxxxxxxxx,glommer@xxxxxxxxx,hannes@xxxxxxxxxxx,kamezawa.hiroyu@xxxxxxxxxxxxxx,mhocko@xxxxxxx,penberg@xxxxxxxxxx,mm-commits@xxxxxxxxxxxxxxx
From: akpm@xxxxxxxxxxxxxxxxxxxx
Date: Fri, 24 Jan 2014 10:58:51 -0800
The patch titled
Subject: memcg, slab: RCU protect memcg_params for root caches
has been removed from the -mm tree. Its filename was
memcg-slab-rcu-protect-memcg_params-for-root-caches.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx>
Subject: memcg, slab: RCU protect memcg_params for root caches
We relocate root cache's memcg_params whenever we need to grow the
memcg_caches array to accommodate all kmem-active memory cgroups.
Currently on relocation we free the old version immediately, which can
lead to use-after-free, because the memcg_caches array is accessed
lock-free (see cache_from_memcg_idx()). This patch fixes this by making
memcg_params RCU-protected for root caches.
Signed-off-by: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxx>
Cc: Glauber Costa <glommer@xxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Balbir Singh <bsingharora@xxxxxxxxx>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Pekka Enberg <penberg@xxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/slab.h | 9 +++++++--
mm/memcontrol.c | 15 ++++++++-------
mm/slab.h | 16 +++++++++++++++-
3 files changed, 30 insertions(+), 10 deletions(-)
diff -puN include/linux/slab.h~memcg-slab-rcu-protect-memcg_params-for-root-caches include/linux/slab.h
--- a/include/linux/slab.h~memcg-slab-rcu-protect-memcg_params-for-root-caches
+++ a/include/linux/slab.h
@@ -513,7 +513,9 @@ static __always_inline void *kmalloc_nod
*
* Both the root cache and the child caches will have it. For the root cache,
* this will hold a dynamically allocated array large enough to hold
- * information about the currently limited memcgs in the system.
+ * information about the currently limited memcgs in the system. To allow the
+ * array to be accessed without taking any locks, on relocation we free the old
+ * version only after a grace period.
*
* Child caches will hold extra metadata needed for its operation. Fields are:
*
@@ -528,7 +530,10 @@ static __always_inline void *kmalloc_nod
struct memcg_cache_params {
bool is_root_cache;
union {
- struct kmem_cache *memcg_caches[0];
+ struct {
+ struct rcu_head rcu_head;
+ struct kmem_cache *memcg_caches[0];
+ };
struct {
struct mem_cgroup *memcg;
struct list_head list;
diff -puN mm/memcontrol.c~memcg-slab-rcu-protect-memcg_params-for-root-caches mm/memcontrol.c
--- a/mm/memcontrol.c~memcg-slab-rcu-protect-memcg_params-for-root-caches
+++ a/mm/memcontrol.c
@@ -3178,18 +3178,17 @@ int memcg_update_cache_size(struct kmem_
if (num_groups > memcg_limited_groups_array_size) {
int i;
+ struct memcg_cache_params *new_params;
ssize_t size = memcg_caches_array_size(num_groups);
size *= sizeof(void *);
size += offsetof(struct memcg_cache_params, memcg_caches);
- s->memcg_params = kzalloc(size, GFP_KERNEL);
- if (!s->memcg_params) {
- s->memcg_params = cur_params;
+ new_params = kzalloc(size, GFP_KERNEL);
+ if (!new_params)
return -ENOMEM;
- }
- s->memcg_params->is_root_cache = true;
+ new_params->is_root_cache = true;
/*
* There is the chance it will be bigger than
@@ -3203,7 +3202,7 @@ int memcg_update_cache_size(struct kmem_
for (i = 0; i < memcg_limited_groups_array_size; i++) {
if (!cur_params->memcg_caches[i])
continue;
- s->memcg_params->memcg_caches[i] =
+ new_params->memcg_caches[i] =
cur_params->memcg_caches[i];
}
@@ -3216,7 +3215,9 @@ int memcg_update_cache_size(struct kmem_
* bigger than the others. And all updates will reset this
* anyway.
*/
- kfree(cur_params);
+ rcu_assign_pointer(s->memcg_params, new_params);
+ if (cur_params)
+ kfree_rcu(cur_params, rcu_head);
}
return 0;
}
diff -puN mm/slab.h~memcg-slab-rcu-protect-memcg_params-for-root-caches mm/slab.h
--- a/mm/slab.h~memcg-slab-rcu-protect-memcg_params-for-root-caches
+++ a/mm/slab.h
@@ -160,14 +160,28 @@ static inline const char *cache_name(str
return s->name;
}
+/*
+ * Note, we protect with RCU only the memcg_caches array, not per-memcg caches.
+ * That said the caller must assure the memcg's cache won't go away. Since once
+ * created a memcg's cache is destroyed only along with the root cache, it is
+ * true if we are going to allocate from the cache or hold a reference to the
+ * root cache by other means. Otherwise, we should hold either the slab_mutex
+ * or the memcg's slab_caches_mutex while calling this function and accessing
+ * the returned value.
+ */
static inline struct kmem_cache *
cache_from_memcg_idx(struct kmem_cache *s, int idx)
{
struct kmem_cache *cachep;
+ struct memcg_cache_params *params;
if (!s->memcg_params)
return NULL;
- cachep = s->memcg_params->memcg_caches[idx];
+
+ rcu_read_lock();
+ params = rcu_dereference(s->memcg_params);
+ cachep = params->memcg_caches[idx];
+ rcu_read_unlock();
/*
* Make sure we will access the up-to-date value. The code updating
_
Patches currently in -mm which might be from vdavydov@xxxxxxxxxxxxx are
origin.patch
mm-vmscan-respect-numa-policy-mask-when-shrinking-slab-on-direct-reclaim.patch
mm-vmscan-move-call-to-shrink_slab-to-shrink_zones.patch
mm-vmscan-remove-shrink_control-arg-from-do_try_to_free_pages.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
